一种新型晶体管级超低功耗精度可配置加法器

Arghavan Mohammad Hassani, Morteza Rezaalipour, M. Dehyadegari
{"title":"一种新型晶体管级超低功耗精度可配置加法器","authors":"Arghavan Mohammad Hassani, Morteza Rezaalipour, M. Dehyadegari","doi":"10.1109/ICCKE.2018.8566643","DOIUrl":null,"url":null,"abstract":"Low power consumption, nowadays, has emerged to be an indispensable factor as there is a growing demand for designing efficient computation-intensive systems and integrating more transistors on chips. With a trade-off between area, delay, power consumption, and accuracy, approximate computing has become a promising solution to address the power efficiency problem for error-tolerant applications such as digital signal processing. Adders are imperative arithmetic components in the applications above. As adder participates in the critical path of most systems, reducing the power consumption of them can contribute to the total system power efficiency. To achieve high flexibility and less fault occurrence when using approximate computation, reconfigurable addition can be beneficial by providing different modes of approximate and accurate operations in multi-bit adder circuits. In this paper, we propose a 16-transistor accurate full adder design based on a 10-transistor full adder for which the threshold loss problem, has been reduced to increase the output voltage swing. This 16-transistor full adder is our baseline for the further proposed configurable bimodal design, which functions as a Lower-part-OR (LOA) Adder in the approximate mode. Having been optimized at transistor level, this configurable bimodal full adder, in the approximate mode, consumes 53% lower power than LOA adder. Moreover, in the accurate mode, the power consumption is reduced by 12% compared to its baseline 16-transistor accurate design.","PeriodicalId":283700,"journal":{"name":"2018 8th International Conference on Computer and Knowledge Engineering (ICCKE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"A Novel Ultra Low Power Accuracy Configurable Adder at Transistor Level\",\"authors\":\"Arghavan Mohammad Hassani, Morteza Rezaalipour, M. Dehyadegari\",\"doi\":\"10.1109/ICCKE.2018.8566643\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Low power consumption, nowadays, has emerged to be an indispensable factor as there is a growing demand for designing efficient computation-intensive systems and integrating more transistors on chips. With a trade-off between area, delay, power consumption, and accuracy, approximate computing has become a promising solution to address the power efficiency problem for error-tolerant applications such as digital signal processing. Adders are imperative arithmetic components in the applications above. As adder participates in the critical path of most systems, reducing the power consumption of them can contribute to the total system power efficiency. To achieve high flexibility and less fault occurrence when using approximate computation, reconfigurable addition can be beneficial by providing different modes of approximate and accurate operations in multi-bit adder circuits. In this paper, we propose a 16-transistor accurate full adder design based on a 10-transistor full adder for which the threshold loss problem, has been reduced to increase the output voltage swing. This 16-transistor full adder is our baseline for the further proposed configurable bimodal design, which functions as a Lower-part-OR (LOA) Adder in the approximate mode. Having been optimized at transistor level, this configurable bimodal full adder, in the approximate mode, consumes 53% lower power than LOA adder. Moreover, in the accurate mode, the power consumption is reduced by 12% compared to its baseline 16-transistor accurate design.\",\"PeriodicalId\":283700,\"journal\":{\"name\":\"2018 8th International Conference on Computer and Knowledge Engineering (ICCKE)\",\"volume\":\"39 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 8th International Conference on Computer and Knowledge Engineering (ICCKE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCKE.2018.8566643\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 8th International Conference on Computer and Knowledge Engineering (ICCKE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCKE.2018.8566643","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

随着设计高效的计算密集型系统和在芯片上集成更多晶体管的需求不断增长,低功耗已经成为一个不可或缺的因素。由于在面积、延迟、功耗和精度之间进行了权衡,近似计算已成为解决容错应用(如数字信号处理)的功率效率问题的一种有前途的解决方案。加法器是上述应用程序中的命令式算术组件。由于加法器参与了大多数系统的关键路径,因此降低系统的功耗有助于提高系统的总功率效率。为了在使用近似计算时实现高灵活性和低故障发生率,可重构加法可以在多位加法器电路中提供不同的近似和精确运算模式。在本文中,我们提出了一种基于10晶体管全加法器的16晶体管精确全加法器设计,该设计减少了阈值损耗问题,以增加输出电压摆幅。这个16晶体管全加法器是我们进一步提出的可配置双峰设计的基准,它在近似模式下用作下半或(LOA)加法器。在晶体管级进行优化后,这种可配置的双峰全加法器在近似模式下的功耗比LOA加法器低53%。此外,在精确模式下,与基准16晶体管精确设计相比,功耗降低了12%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Novel Ultra Low Power Accuracy Configurable Adder at Transistor Level
Low power consumption, nowadays, has emerged to be an indispensable factor as there is a growing demand for designing efficient computation-intensive systems and integrating more transistors on chips. With a trade-off between area, delay, power consumption, and accuracy, approximate computing has become a promising solution to address the power efficiency problem for error-tolerant applications such as digital signal processing. Adders are imperative arithmetic components in the applications above. As adder participates in the critical path of most systems, reducing the power consumption of them can contribute to the total system power efficiency. To achieve high flexibility and less fault occurrence when using approximate computation, reconfigurable addition can be beneficial by providing different modes of approximate and accurate operations in multi-bit adder circuits. In this paper, we propose a 16-transistor accurate full adder design based on a 10-transistor full adder for which the threshold loss problem, has been reduced to increase the output voltage swing. This 16-transistor full adder is our baseline for the further proposed configurable bimodal design, which functions as a Lower-part-OR (LOA) Adder in the approximate mode. Having been optimized at transistor level, this configurable bimodal full adder, in the approximate mode, consumes 53% lower power than LOA adder. Moreover, in the accurate mode, the power consumption is reduced by 12% compared to its baseline 16-transistor accurate design.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信